迈向根记忆：面向个性化大语言模型的隐式逻辑记忆检索基准与增强
Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs
AI总结：
针对现有记忆系统依赖语义相似性而忽略逻辑关键记忆的问题，构建首个高质量基准IMLogic，并提出根记忆表示与RootMem框架，通过结构化逻辑记忆提升个性化LLM检索性能。
摘要：
记忆系统对于个性化大语言模型（LLM）至关重要。然而，现有系统中的检索方法主要依赖语义相似性，可能遗漏语义重叠有限但逻辑关键的记忆。当前基准不足以评估这一问题。为填补这一空白，我们构建了IMLogic，这是首个针对长对话场景中隐式逻辑记忆检索的高质量基准。受此挑战启发，我们引入根记忆，一种结构化的、保留决策的表示，从长期用户历史中提炼可重用的个性化逻辑。随后提出RootMem，一个即插即用框架，首先将原始历史提炼为结构化根记忆，然后使用基于LLM的路由器激活逻辑相关的记忆，用个性化决策逻辑补充语义检索。大量实验表明，RootMem显著优于最强的检索基线，并持续提升现有记忆代理的准确性。我们的基准和代码将在此URL提供。
英文摘要：
Memory systems are essential for personalized Large Language Models (LLMs). However, existing retrieval methods in these systems primarily rely on semantic similarity, potentially missing logically critical memories with limited semantic overlap. Current benchmarks remain inadequate for evaluating this problem. To address this gap, we construct IMLogic, the first high-quality benchmark targeting implicit logical memory retrieval in long-dialogue scenarios. Motivated by this challenge, we introduce root memory, a structured, decision-preserving representation that distills reusable personalized logic from long-term user histories. We then propose RootMem, a plug-and-play framework that first distills raw histories into structured root memories and then uses an LLM-based router to activate logically relevant ones, complementing semantic retrieval with personalized decision logic. Extensive experiments demonstrate that RootMem significantly outperforms the strongest retrieval baselines and consistently boosts the accuracy of existing memory agents. Our benchmark and codes will be available at https://anonymous.4open.science/r/IMLogic-DBB3.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
